Skip to main content

Mana-Agent

Repository execution uses MainAgent → CodingAgent → deterministic ToolRunner. Repository knowledge is shared through the persistent Repository Evidence Board; investigation and understanding are TaskBoard tasks that use the selected coding engine. Execution activity exposes commands, working directories, live output, observed diffs, and retained operation details. External Codex keeps its own tool loop with explicit backend provenance. See the execution and verification contract.

Inference uses Mana's native OpenAI Responses, Chat Completions and Anthropic Messages adapters. Model capabilities come from scoped evidence and explicit user overrides. Repository search needs no vector index or embedding credential. See configuration and user-owned acceptance.

Mana-Agent

Think beyond prompts. Build beyond boundaries.

Your AI-powered execution workspace.
One goal. Multiple agents. Real tools. Verified results.

Python License GitHub

English · العربية · বাংলা · Brezhoneg · Bosanski · Dansk · Deutsch · Español · فارسی · Français · Ελληνικά · Italiano · 日本語 · 한국어 · Norsk · Polski · Русский · ไทย · Türkçe · Українська · Tiếng Việt · 简体中文 · 繁體中文

Get Started · Capabilities


What if your AI could do more than answer?

Most AI tools stop at the answer.

You ask a question. They generate a response. Then you're left to figure out what to do next.

Mana-Agent is built for what happens after the answer.

It can understand your goals, explore your environment, plan actions, coordinate specialized agents, use real tools, and verify outcomes.

Not just for writing code.

For researching, building, debugging, managing, automating, and solving complex tasks across connected systems.

For unresolved coding bugs, the Main Model can select bounded, version-aware web/GitHub research after local investigation and return sourced findings to the same coding task. Both coding engines use the existing Coding Activity stream. See coding research configuration and recovery.

You define the destination. Mana-Agent helps navigate the journey.

Meet Mana-Agent

Mana-Agent is an open-source, Python-based AI agent orchestration platform combining an autonomous execution loop, specialized agents, persistent task management, supervised tool execution, and extensible integrations.

It brings multiple capabilities into one coordinated environment:

  • Understand: Analyze repositories, documents, APIs, and available evidence before taking action.
  • Decide: Select suitable models, agents, tools, and execution strategies.
  • Execute: Use coding tools, browser automation, external services, and connected systems.
  • Coordinate: Distribute work among specialized agents while tracking dependencies and progress.
  • Remember: Reuse authorized context, decisions, and lessons across relevant tasks.
  • Verify: Evaluate actual outcomes rather than treating tool completion as success.
  • Continue: Replan, recover, or request human intervention when the goal remains unresolved.

The objective is simple:

Make AI useful not only for thinking about work, but for carrying work through to a trustworthy result.

What can Mana-Agent do?

Your challenge What Mana-Agent can help with
"I don't understand this codebase." Explore architecture, dependencies, execution flows, and relevant files.
"Something is broken." Investigate symptoms, identify likely causes, propose fixes, and run verification.
"I want to build something complex." Decompose goals, coordinate coding agents, manage dependencies, and review implementation.
"This task has too many steps." Track progress through the autonomous loop, TaskBoard, and execution supervisor.
"I need information from an API." Inspect API documentation, validate requests, and execute supported operations.
"I keep repeating this workflow." Create automations or teach repeatable actions using Teach Mode.
"I want AI to work across tools." Integrate browser, Git, SSH, email, Telegram, protocols, and external services.
"What happened during execution?" Inspect activity, tools, decisions, errors, checkpoints, and artifacts.

One interface. Many kinds of work.

> Explain how authentication works in this repository.

> Find why the latest deployment failed.

> Plan and implement a new feature, then run its tests.

> Read this API documentation and help me call the right endpoint.

> Analyze these files and produce an actionable report.

> Break this project into independent tasks and track progress.

> Review previous mistakes before attempting this operation again.

Mana-Agent is designed to support both focused questions and multi-step workflows.


Quick Start

1. Install

Requires Python 3.10–3.14.

Recommended installation with pipx:

pipx install git+https://github.com/manaplatform/mana-agent.git

Or install directly from the repository:

git clone https://github.com/manaplatform/mana-agent.git
cd mana-agent

python3 -m venv .venv
source .venv/bin/activate

python -m pip install -e .

2. Configure

mana-agent --configure

Configure your model provider, credentials, model preferences, and supported capabilities. The setup CLI includes OpenAI-compatible providers such as xAI (Grok); see provider configuration for setup details.

3. Start

cd /path/to/your/project
mana-agent

You're ready.

Execution & Approval Modes

Mana-Agent supports three execution approval modes:

  • default: Interactive approval behavior (prompts for mutating/consequential operations).
  • auto_approve_safe: Automatically approves explicitly classified safe operations (e.g., non-destructive shell, test runs, linters, local git queries); prompts for destructive actions.
  • full_access: Automatically approves all supported operations without interactive confirmation prompts while preserving operating-system boundaries and security controls.
# Enable Full Access Mode via CLI
mana-agent --full-access
mana-agent --approval-mode full_access

# Or set via environment variable
export MANA_AGENT_APPROVAL_MODE=full_access

# Or configure in ~/.mana/config.toml
# [execution]
# approval_mode = "full_access"

Start with a question about your repository, ask for an investigation, or describe something you want to accomplish.

Your first task doesn't need to be complicated.

Try:

Analyze this project and explain its architecture,
main components, dependencies, and potential risks.

4. Explore the dashboard

mana-agent dashboard --root-dir .

The optional dashboard provides another way to interact with Mana-Agent, inspect activity, and manage workflows.


Live agent activity

Textual chat, Rich terminal chat, and the dashboard show observable operations, agent explanations when provided, and supported public provider summaries while work is running. The Textual chat shows one inline execution stream per turn. Expand an operation for its redacted command, available output, diff, and provenance. The Rich terminal and dashboard keep their existing activity views. Concurrent agents retain their task, attempt, and operation identities. Verification is recorded independently of backend completion.

Use /activity minimal, /activity normal (default), or /activity verbose to persist MANA_ACTIVITY_VISIBILITY through the existing user configuration. /activity shows recent recorded activity. In Textual chat, Ctrl+End returns to the latest output, Ctrl+O attaches a file, and Esc requests interruption of the session’s active execution. Begin with / to find available commands and press Tab to insert the selected command. Assistant replies offer Copy mode for selecting the Markdown source. Activity details use the public projection, which excludes private reasoning, credentials, prompts, and raw invocation arguments.

During an active TUI or dashboard turn, submit text to steer that execution. The user row appears pending immediately and follows recorded delivery and acknowledgement. Dashboard steering is text-only and requires the same runtime to own the live session. Execution approvals appear above the Textual composer. Ctrl+G focuses the choices. Plan Mode activity describes planning and artifact saving. Its revision review and clarification forms use the existing workflow.

See activity architecture, limitations, regression rules, and user verification.

Use /plan to review a repository change before approving its exact revision. In ordinary chat, describe the failure to start an evidence-based investigation. See AUTO, DEBUG, and PLAN for ordinary coding and exact revision approval.

License

Mana-Agent is open source under the MIT License.


Mana-Agent
From intention to execution. From execution to evidence.

Get Started · GitHub · Report an Issue · Explore the Docs

Have a goal in mind? Start with Mana.

Metadata

Release files for mana-agent 0.15.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mana-agent 0.15.1
File Size Uploaded Provenance Actions
mana_agent-0.15.1.tar.gz 2.8 MB With provenance Details for mana_agent-0.15.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for mana-agent 0.15.1
File Interpreter ABI Platform Actions
mana_agent-0.15.1-py3-none-any.whl Python 3 none any Details for mana_agent-0.15.1-py3-none-any.whl

Total release size: 5.5 MB

Release files / mana_agent-0.15.1.tar.gz

Download URL mana_agent-0.15.1.tar.gz
Size 2.8 MB
Tags Source
SHA-256 checksum
How to use checksums
3db0170385258f906058b8b2ebe71db4865b9428e8836c24e12318d37e3f6a0c
BLAKE2b-256 checksum
How to use checksums
cc5f949404c13bf283779cb45644060277b3300a5f101d0e09983905e3fc96e3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.13

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 21, 2026.

Transparency log

Release files / mana_agent-0.15.1-py3-none-any.whl

Download URL mana_agent-0.15.1-py3-none-any.whl
Size 2.8 MB
Tags Python 3
SHA-256 checksum
How to use checksums
426fa6a5926f294c58cf294218a47344c03a60c93902fd05698d246994f6059e
BLAKE2b-256 checksum
How to use checksums
103bd45034b775eaf36c1489235271beb8a4622224283f3e03611ac8034cf846
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.13

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 21, 2026.

Transparency log

Security for mana-agent 0.15.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for mana_agent-0.15.1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 21, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.15.1 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page